[Back to MCP overview](https://www.summerengine.com/mcp)

Summer Engine MCP guide

# How to make games for free with local LLMs in Summer Engine

Run a free local model — Ollama, LM Studio, or Goose — and build real games in Summer Engine through MCP. No subscription; your GPU does the thinking. Summer Engine is the desktop game engine; Local LLMs drives it through MCP with a model running on your own hardware.

$ npx -y summer-engine@latest setup lm-studio --yes

A local LLM runs free on your GPU. Summer Engine shows the game.

01

## Summer is free for MCP use

Download the desktop engine and connect it to your agent. The model runs on your own hardware, with no AI subscription and no per-message cost.

02

## Open Local LLMs

Run a free local model on your own GPU. The setup writes the MCP config so {agentLabel} can drive the engine directly.

03

## Run a Summer game

The local model writes code. Summer Engine shows the Summer game, runs Play mode, and helps inspect errors. Export still requires the target templates and toolchains.

Install

## Connect Summer to Local LLMs

1. 1  
### Install Summer Engine  
Downloads the desktop engine app, about 1 GB. Skip it if Summer Engine is already installed, or if you only need assets and video for a game built in another engine.  
$ npx -y summer-engine@latest install
2. 2  
### Sign in  
Opens your browser once. The CLI and the engine share the session.  
$ npx -y summer-engine@latest login
3. 3  
### Connect Local LLMs  
Writes the summer-engine MCP config and installs the Summer game-dev skills.  
$ npx -y summer-engine@latest setup lm-studio --yes
4. 4  
### Restart and build  
Open LM Studio, toggle on the summer-engine MCP server in the Program tab, and raise the loaded model's context length to 32k or higher.

Local setup notes

## The 2026 specifics.

### Easiest: LM Studio

One app for the model and the MCP host. The setup command above writes the config; pick a model, raise its context to 32k+, and build. See the LM Studio guide for details.

### Terminal: OpenCode + Ollama

The most common 2026 pairing. Ollama serves the model, OpenCode is the agent. Start Ollama with OLLAMA\_CONTEXT\_LENGTH=65536 — the 4k default silently breaks MCP. See the Ollama guide.

### What to run

gpt-oss-20b on 12–16 GB of VRAM, Qwen3-Coder-30B or Gemma 4 27B on 24 GB, Q4\_K\_M quantization or better. Engine control and asset search are free; cloud generation uses credits.

Why this matters

## Local LLMs runs free on your hardware. Summer Engine shows the game.

A capable local model can operate a real engine through MCP. It opens scenes, places objects, runs the project and reads errors. Your GPU does the thinking, with no subscription and no per-token bill, and your prompts never leave your machine.

Other setup guides

## Start with Local LLMs. Build inside Summer.

Install the desktop app for free, connect the MCP server, and make your first scene playable. No subscription required.

[Download](https://www.summerengine.com/download)

[Docs ](https://docs.summerengine.com/mcp/overview)

Source: https://www.summerengine.com/mcp/how-to-make-games-for-free-with-local-llms

---

## Machine-readable resources

- Site index for agents: https://www.summerengine.com/llms.txt
- Full inlined content: https://www.summerengine.com/llms-full.txt
- Porting catalog: https://www.summerengine.com/llms-porting.txt
- Structured catalog: https://www.summerengine.com/agent-catalog.json
- Sitemap: https://www.summerengine.com/sitemap.xml
- Developer resources: https://www.summerengine.com/docs